Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/gonzi-stack/deepseek-skills/deepseek-debugnpx skills add gonzi-stack/deepseek-skills --skill deepseek-debuggit clone --depth 1 https://github.com/gonzi-stack/deepseek-skillsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00080 | $0.02484 |
| Opus 5 | $0.00040 | $0.01242 |
| Sonnet 5 | $0.00016 | $0.00497 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade A, and why
deepseek-debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Bug Diagnosis Skill — Universal
Un error no es un obstáculo — es información. Tu trabajo es extraer esa información sistemáticamente antes de escribir una sola línea de corrección.
Principio fundamental
Nunca corrijas lo que no entendés. Cada corrección sin diagnóstico completo es una apuesta. A veces funciona. Siempre deja deuda técnica oculta.
El flujo correcto es siempre:
ERROR → LEER → ENTENDER → LOCALIZAR → HIPÓTESIS → VERIFICAR → CORREGIR
No:
ERROR → ADIVINAR → CAMBIAR COSAS → REZAR
FASE 1 — Leer el error completo
1.1 Nunca leer solo la primera línea
Los errores tienen estructura. La primera línea es el síntoma. Las líneas siguientes son la causa.
TypeError: Cannot read properties of undefined (reading 'user')
at createContext (src/server/context.ts:45:32) ← dónde pasó exactamente
at src/app/api/route.ts:12:5 ← cómo llegamos ahí
- Línea 1: qué pasó
- Línea 2+: dónde pasó (archivo, línea, columna) y el call stack
Leer solo la primera línea y adivinar la causa es un error de principiante.
1.2 Clasificar el tipo de error antes de actuar
| Tipo | Señales | Dónde buscar |
|---|---|---|
| TypeError / AttributeError | undefined is not a function, has no attribute |
El objeto era null/undefined cuando no debía serlo |
| Error de tipos estáticos | Type 'X' is not assignable to 'Y', incompatible types |
Discrepancia entre tipos declarados y reales |
| Error de validación | ZodError, ValidationError, schema mismatch | Input no cumple el schema esperado |
| Error de DB | tabla inexistente, columna inválida, constraint violada, connection refused | Schema, nombre de tabla/columna, conexión |
| Error de imports | Module not found, Cannot resolve, ImportError |
Path incorrecto, export faltante, módulo no instalado |
| Error de runtime genérico | 500 Internal Server Error, uncaught exception |
Logs del servidor para ver el error real |
| Error de configuración | variables de entorno faltantes, config inválida | Archivos de configuración, .env |
| Error de auth | 401, 403, sesión nula inesperada | Middleware, tokens, cookies |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 309 lines · 80 tokens per session scan A 8db53605b32c
deepseek-debug is a skill published in the GitHub repository gonzi-stack/deepseek-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 2,484 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…